Commit
•
478ba65
1
Parent(s):
b013e7f
Update README.md
Browse files
README.md
CHANGED
|
@@ -15,6 +15,21 @@ license: apache-2.0
|
|
| 15 |
|
| 16 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
| 17 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
## Merge Details
|
| 19 |
### Merge Method
|
| 20 |
|
|
|
|
| 15 |
|
| 16 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
| 17 |
|
| 18 |
+
## 🏆 Evaluation
|
| 19 |
+
|
| 20 |
+
### [kormedmcqa(한국어 의학 벤치마크)](https://huggingface.co/datasets/sean0042/KorMedMCQA)
|
| 21 |
+
|
| 22 |
+
| Model | Doctor | Nurse | Pharm | Avg |
|
| 23 |
+
|------------------------------------------|-------|-------|-------|-------|
|
| 24 |
+
| gpt-4-0613 | 75.09 | 85.86 | 83.22 | 81.39 |
|
| 25 |
+
| **iRASC/BioLlama-Ko-8B** | 45.26 | 63.37 | 58.47 | 55.70 |
|
| 26 |
+
| gpt-3.5-turbo-0613 | 41.75 | 62.18 | 56.35 | 53.43 |
|
| 27 |
+
| llama2-70b | 42.46 | 63.54 | 53.26 | 53.09 |
|
| 28 |
+
| SOLAR-10.7B-v1.0 | 37.19 | 55.54 | 54.07 | 48.93 |
|
| 29 |
+
| ProbeMedicalYonseiMAILab/medllama3-v20 | 37.19 | 54.68 | 50.65 | 47.51 |
|
| 30 |
+
| beomi/Llama-3-Open-Ko-8B | 38.95 | 53.49 | 46.09 | 46.18 |
|
| 31 |
+
|
| 32 |
+
|
| 33 |
## Merge Details
|
| 34 |
### Merge Method
|
| 35 |
|